nemotron-cascade-2

1,601 Downloads Updated 14 hours ago

An open 30B MoE model from NVIDIA with 3B activated parameters that delivers strong reasoning and agentic capabilities.

tools thinking 30b

ollama run nemotron-cascade-2

curl http://localhost:11434/api/chat \
  -d '{
    "model": "nemotron-cascade-2",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='nemotron-cascade-2',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'nemotron-cascade-2',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code ollama launch claude --model nemotron-cascade-2

Codex ollama launch codex --model nemotron-cascade-2

OpenCode ollama launch opencode --model nemotron-cascade-2

OpenClaw ollama launch openclaw --model nemotron-cascade-2

Models

View all →

Name

3 models

Size

Context

Input

nemotron-cascade-2:latest

24GB · 256K context window · Text · 14 hours ago

nemotron-cascade-2:latest

24GB

256K

Text

nemotron-cascade-2:30b

latest

24GB · 256K context window · Text · 16 hours ago

nemotron-cascade-2:30b latest

24GB

256K

Text

Readme

Nemotron-Cascade-2-30B-A3B is an open 30B MoE model with 3B activated parameters that delivers strong reasoning and agentic capabilities. It achieves gold medal performance in both the 2025 International Mathematical Olympiad (IMO) and the International Olympiad in Informatics (IOI). It operates in both thinking and instruct (non-reasoning) modes.